import os

import numpy as np

import pandas as pd

import matplotlib as mpt

import seaborn as sns

import plotly.express as px

import plotly.graph_objects as go

​

data = pd.read_csv('Latest Covid-19 India Status.csv')

df = data.copy() #make a copy of the original data and only make changes to the copy

df.head() #display some of the data

df.shape #get number of (rows, columns)

df.columns #these are the features

df.info() #no null values, data type = integer, float, strings

df.duplicated().sum() #get number of duplicate values

df.describe() #get statistics for the given data

df.corr() #get correlation between different values 

          #a correlation above 0.7 would be considered significant

mpt.pyplot.figure(figsize = (9,6))

sns.heatmap(df.corr(), annot=True)

​

#from the correlation heatmap we can see that total cases has a high correlation with deaths, active and discharge

fig = px.scatter_matrix(df, dimensions=["Total Cases", "Active", "Discharged", "Deaths"], color=df['State/UTs']) 

fig.update_layout(

    width=1200,

    height=1000,

)

​

fig.show()

df_sorted = df.copy().sort_values('Total Cases', ascending = False).reset_index(drop=True)

#sort values in descending order

#to get top 15 countries with maximum cases

df_sorted

#get total number of cases in india here

df_allIndia = df_sorted.copy()

allIndia=[]

​

allIndia.append('All India') #index=0

totalCases=0

for i in range (36):

    totalCases = totalCases + int(df_sorted['Total Cases'][i])

allIndia.append(totalCases) #index1

active=0

for i in range (36):

    active = active + int(df_sorted['Active'][i])

allIndia.append(active)#index2

discharged=0

for i in range (36):

    discharged = discharged + int(df_sorted['Discharged'][i])

allIndia.append(discharged) #index3

deaths=0

for i in range (36):

    deaths = deaths + int(df_sorted['Deaths'][i])

allIndia.append(deaths) #index4

​

activeRatio = round((100*active)/totalCases, 2)

allIndia.append(activeRatio) #index5

​

dischargeRatio =  round((100*discharged)/totalCases, 2)

allIndia.append(dischargeRatio) #index5

​

deathRatio = round((100*deaths)/totalCases, 2)

allIndia.append(deathRatio) #index5

​

population=0

for i in range (36):

    population = population + int(df_sorted['Population'][i])

allIndia.append(population) #index1

​

df_allIndia.loc[len(df_allIndia)] = allIndia

df_allIndia = df_allIndia.sort_values('Total Cases', ascending = False).reset_index(drop=True)

df_allIndia

#let's try to figure out the ratio of people affected for india as well as each state

​

df_allIndia['(%) of Affected People']=round((df_allIndia['Total Cases']*100)/df_allIndia['Population'], 2)

df_allIndia

df_allIndia2 = df_allIndia.iloc[1:, :]

​

fig = px.pie(df_allIndia2, values='(%) of Affected People', names = df_allIndia2['State/UTs'], title="(%) of people affected in each state with respect to the total population of the state" )

fig.show()

#add a pie chart for total cases

fig = px.pie(df_sorted, values='Total Cases', names = df_sorted['State/UTs'], title="Covid cases all over India in (%)" )

fig.show()

​

fig = go.Figure()

for i in range (10) :

    fig.add_trace(go.Bar(name = df_sorted['State/UTs'][i], x = df_sorted.columns[1:5], y = df_sorted.loc[i][1:5]))

fig.update_layout(title = {"text":f'Top 10 affected states'})

fig.show()    

#plot number of cases per state and view death ratio

px.bar(df_sorted, x="Total Cases",y="State/UTs", color="Death Ratio", width=900, height=600)

#death ratio is highest in punjab

#plot number of cases per state and view discharge ratio

px.bar(df_sorted, x="Total Cases",y="State/UTs", color="Discharge Ratio",  width=700, height=900)

#discharge ratio is highest in Arunachal pradesh

#now lets look at active ratio

px.bar(df_sorted, x="Total Cases",y="State/UTs", color="Active Ratio",  width=900, height=600)

#Mizoram has the most active cases

fig = px.choropleth(

    df,

    geojson="https://gist.githubusercontent.com/jbrobst/56c13bbbf9d97d187fea01ca62ea5112/raw/e388c4cae20aa53cb5090210a42ebb9b765c0a36/india_states.geojson",

    featureidkey='properties.ST_NM',

    locations='State/UTs',

    color='Active',

    color_continuous_scale='Greens'

)

​

fig.update_geos(fitbounds="locations", visible=False)

​

fig = px.choropleth(

    df,

    geojson="https://gist.githubusercontent.com/jbrobst/56c13bbbf9d97d187fea01ca62ea5112/raw/e388c4cae20aa53cb5090210a42ebb9b765c0a36/india_states.geojson",

    featureidkey='properties.ST_NM',

    locations='State/UTs',

    color='Deaths',

    color_continuous_scale='Reds'

)

​

fig.update_geos(fitbounds="locations", visible=False)

​

fig = px.choropleth(

    df,

    geojson="https://gist.githubusercontent.com/jbrobst/56c13bbbf9d97d187fea01ca62ea5112/raw/e388c4cae20aa53cb5090210a42ebb9b765c0a36/india_states.geojson",

    featureidkey='properties.ST_NM',

    locations='State/UTs',

    color='Total Cases',

    color_continuous_scale='Blues'

)

​

fig.update_geos(fitbounds="locations", visible=False)

​

fig = px.choropleth(

    df,

    geojson="https://gist.githubusercontent.com/jbrobst/56c13bbbf9d97d187fea01ca62ea5112/raw/e388c4cae20aa53cb5090210a42ebb9b765c0a36/india_states.geojson",

    featureidkey='properties.ST_NM',

    locations='State/UTs',

    color='Discharged',

    color_continuous_scale='Purples'

)

​

fig.update_geos(fitbounds="locations", visible=False)

​

fig = px.histogram(df_sorted, 'Total Cases',             

                   color="State/UTs",

                   title="<b>Average cases per state</b>", width=600, height=400)

​

fig.add_vline(x=df_sorted['Total Cases'].mean(), line_width=2, line_dash="dash", line_color="black")

​

fig.show()